期刊文献+

桩端压力注浆桩承载力径向基遗传神经网络研究 被引量:1

Radial Base Genetic Neural Network Study of Bottom-Grouting Pile Bearing Capacity
下载PDF
导出
摘要 压力注浆是目前有效解决桩基施工工艺固有缺陷的有效手段,影响注浆加固效果的因素较多。本文采用径向基遗传神经网络实现持力层性状、桩长桩径、注浆压力、注浆量与承载力增大系数之间的非线性映射,研究结果表明,承载力增大系数随着注浆压力的增加而明显增加;存在最大的桩端注浆量,当超过最大的注浆量以后,承载力增大系数几乎不再增加。 Bottom-grouting is an effective means to solve inherent vice of pile construction craftwork at present. There are many factors to affect the grouting consolidation effect. In this paper the radial base genetic neural networks are used to implement the non-liner mapping between the increment coefficient of bearing capability and the character of holding-layer, pile length, pile diameter, grouting pressure, grouting volume. Results indicate that the accretion coefficient of bearing capability accelerates with the increment of grouting pressure, the most grouting volume exists and the coefficient of bearing capability no more increases when the grouting volume exceeds its most grouting volume.
出处 《山东交通学院学报》 CAS 2003年第4期7-13,共7页 Journal of Shandong Jiaotong University
关键词 注浆桩 遗传神经网络 径向基 承载力 grouting pile genetic neural network radial base bearing capacity
  • 相关文献

参考文献4

二级参考文献11

共引文献65

引证文献1

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部